Answers are grounded in this paper and cite their sources.
Salient object detection (SOD) is fundamental to computer vision, yet deep learning approaches often suffer from high computational costs, limiting deployment on resource-constrained devices. We propose a Lightweight Multi-scale Weight Pruning Network (LMWP-Net) to balance high performance with low complexity. LMWP-Net employs an encoder–decoder architecture featuring two key components: a Multi-scale Weight Pruning Module (MWPM) for efficient feature extraction and redundancy reduction, and a Multi-scale Attention Fusion Module (MAFM) for effective integration via attention mechanisms. Extensive experiments on public datasets demonstrate that LMWP-Net consistently outperforms existing lightweight methods and achieves competitive accuracy against state-of-the-art models. Remarkably, compared to the prominent BANet, LMWP-Net achieves a 94.6% reduction in parameters and a 99.5% reduction in FLOPs, validating its superior efficiency and effectiveness for real-time applications. The implemented code is publicly available at https://github.com/IMOP-lab/LMWP-Net .
No takes yet. Share an insight, caveat, or question.
Sheng et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: